The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documentation includes instructions for the agent to run local Python scripts, specifically scripts/init_skill.py for setting up new skill directories and scripts/package_skill.py for validation and distribution. These are functional components of the tool.
[INDIRECT_PROMPT_INJECTION]: The skill creation process involves gathering requirements and examples from users to generate instructions for new skills. Ingestion points: User-provided examples in Step 1 and Step 4. Boundary markers: None identified in the provided markdown. Capability inventory: Ability to execute local Python scripts and generate file structures via init_skill.py. Sanitization: The skill does not explicitly mention sanitization of user-provided content before it is incorporated into the generated SKILL.md files.

skill-creator